SamPO - a jiazhengli Collection

jiazhengli 's Collections

MCTS with Preference Optimisation

SamPO

AERA

SamPO

updated Oct 14

Resources for EMNLP 2024 Paper: Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence

jiazhengli/Pythia-2.8B-HH-RLHF-Iterative-SamPO

Text Generation • Updated Jun 17 • 21
jiazhengli/Pythia-2.8B-TLDR-Iterative-SamPO

Text Generation • Updated Jun 17 • 12
Junrulu/Llama-3-8B-Instruct-Iterative-SamPO

Text Generation • Updated Jun 14 • 22
Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled KL Divergence

Paper • 2406.10957 • Published Jun 16 • 1